Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling
This addresses the challenge of learning densities on SO(3) manifolds for probabilistic regression of correlated 3D rotations, with implications for domains like robotics and human pose modeling.
The paper tackles the problem of probabilistic human pose modeling by introducing HuProSO3, a normalizing flow model that operates on a product space of SO(3) manifolds, resulting in superior modeling accuracy in three applications and exact likelihood evaluation.
Normalizing flows have proven their efficacy for density estimation in Euclidean space, but their application to rotational representations, crucial in various domains such as robotics or human pose modeling, remains underexplored. Probabilistic models of the human pose can benefit from approaches that rigorously consider the rotational nature of human joints. For this purpose, we introduce HuProSO3, a normalizing flow model that operates on a high-dimensional product space of SO(3) manifolds, modeling the joint distribution for human joints with three degrees of freedom. HuProSO3's advantage over state-of-the-art approaches is demonstrated through its superior modeling accuracy in three different applications and its capability to evaluate the exact likelihood. This work not only addresses the technical challenge of learning densities on SO(3) manifolds, but it also has broader implications for domains where the probabilistic regression of correlated 3D rotations is of importance.